Single lectures
dhkwak-Introduction of Deep Reinforcement Learning
rlcode-understand a3c architecture
rlcode-implement reinforcement algorithms
actor critic architecture to deal with cartpole environment
a3c architecture to deal with breakout atari game environment
jwcleo-manually build environment, gui, agent
deal_with_cartpole_with_a2c
single tutorial code
actor critic dealing with pendulum environment with keras
awjuliani-Concepts of reinforcement learning and practical codes
q learning with q table
q learning with q network
q learning with q network which has one state and multiple actions
q learning with q network which has multiple states and multiple actions
q learning with q network where you use policy gradient based agent in cartpole question
build model network and policy network reflecting real environment for RL question
q learing with DoubleDQN and DuelingDQN for navigation task
deal with "partial obserbability markov decision process" question with deep recurrent q network and convolution layer
SHKim-Reinforcement learning and practical codes
Lec_002_Playing_OpenAI_GYM_Games
Lab_002_Playing_OpenAI_GYM_Games
Lec_003_Dummy_Q_learning_using_table
Lab_003_Dummy_Q_learning_using_table
Lec_004_Q-learning_using_table_Exploit_and_exploration_Discounted_reward
Lab_004_Q-learning_using_table_Exploit_and_exploration_Discounted_reward_using_adding_random_noise_to_Q_values
Lab_004_Q-learning_using_table_Exploit_and_exploration_Discounted_reward_using_adding_e_greedy
Lec_005_Q-learning_on_nondeterministic_worldy
Lab_005_001_Play_FrozenLake_game_on_non_deterministic_environement
Lab_005_002_Use_Q_mentor_on_non_deterministic_environement
Lab_005_003_Use_Q_mentor_with_learning_rate_on_non_deterministic_environement
Lec_006_Q-network
Lab_006_001_Q-network_grid_world
007_lec_DQN
007_000_lab_random_cartpole
007_001_lab_q_net_cartpole
007_002_lab_dqn_2013_cartpole
007_003_lab_dqn_2015_cartpole
007_001_lab_DQN 1 (NIPS 2013)
007_002_lab_DQN 2 (Nature 2015)
010_001_Actor_Critic
PangYoLab - Reinforcement learning theory
001_Introduction_to_RL
002_Markov_decision_process
003_Planning_by_dynamic_programming
PangYoLab - Review AlphaGo paper
001 Monte Carlo Tree Search
002
003